Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/wittyreference/twilio-claude-plugin/conversation-relaynpx skills add wittyreference/twilio-claude-plugin --skill conversation-relaygit clone --depth 1 https://github.com/wittyreference/twilio-claude-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wittyreference/twilio-claude-plugin/conversation-relay)<a href="https://agentmods.dev/skills/wittyreference/twilio-claude-plugin/conversation-relay"><img src="https://agentmods.dev/badge/skills/wittyreference/twilio-claude-plugin/conversation-relay.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00012 | $0.02364 |
| Opus 5 | $0.00006 | $0.01182 |
| Sonnet 5 | $0.00002 | $0.00473 |
| Haiku 4.5 | $0.00001 | $0.00236 |
Grade A, and why
conversation-relay scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| ngrok tunnel dies mid-session | Tunnel expires/disconnects | Verify with `curl localhost:4040` | How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conversation Relay Functions Context
Service: prototype-ai (AI_BASE_URL). Deploy: ./scripts/deploy-services.sh dev
For LLM integration code, ngrok setup, full configuration, and code patterns, see REFERENCE.md.
Files
Public Handlers
| File | Access | Description |
|---|---|---|
ai-assistant-inbound.js |
Public | Connects incoming calls to ConversationRelay AI agent |
relay-handler.js |
Public | Entry point for connecting phone calls to LLM-powered voice agents |
Callbacks
| File | Access | Description |
|---|---|---|
transcript-complete.protected.js |
Protected | Handles Voice Intelligence transcript completion callback; sends SMS summary |
Demo Flow
| File | Access | Description |
|---|---|---|
start-ai-demo.protected.js |
Protected | Initiates outbound AI demo call with recording and ConversationRelay |
finalize-demo.protected.js |
Protected | Processes completed demo call — stores transcript in Sync, sends SMS |
Agent-to-Agent Testing Infrastructure
| File | Access | Description |
|---|---|---|
agent-a-inbound.protected.js |
Protected | Inbound call handler for Agent A (questioner) |
agent-b-inbound.protected.js |
Protected | Inbound call handler for Agent B (answerer) |
start-agent-test.protected.js |
Protected | Test orchestrator that initiates agent-to-agent calls |
validate-agent-test.protected.js |
Protected | Validates agent-to-agent test results via Sync transcripts |
Payment Testing Infrastructure
| File | Access | Description |
|---|---|---|
payment-test-start.protected.js |
Protected | Orchestrates 3-participant conference (Payment Agent, Customer Agent, DTMF Injector) |
payment-agent-inbound.protected.js |
Protected | Payment Agent ConversationRelay handler |
customer-agent-inbound.protected.js |
Protected | Customer Agent ConversationRelay handler |
dtmf-hold.js |
Public | Hold endpoint for DTMF Injector — returns long pause TwiML |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 205 lines · 12 tokens per session scan A e1ba89a0a5ac
conversation-relay is a skill published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 2,364 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…